INDEX

Explanations

references to benefits or advantages

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-1.14

 Anſ

-1.12

Efq

-1.07

StoryboardSegue

-1.06

 Houſe

-1.05

 ་་

-1.03

 surla

-1.02

Eſ

-1.02

 Theſe

-1.01

 ―――――

-1.01

POSITIVE LOGITS

0.70

 advantage

0.70

mal

0.67

0.65

in

0.60

↵↵

0.59

 practice

0.58

Bay

0.58

0.57

en

0.57

Activations Density 0.097%

references to benefits or advantages

No Comments

No Known Activations